In this post, you will learn why deep learning is called as deep learning.
You may recall that deep learning is a subfield of machine learning. One of the key difference between deep learning and machine learning is in the manner the representations / features of data is learnt. In machine learning, the representations of data need to be hand-crafted by the data scientists. In deep learning, the representations of data is learnt automatically as part of learning process.
As a matter of fact, in deep learning, layered representations of data is learnt. The layered representations of data are learnt via models called as neural networks. The diagram below represents the multiple layers using which the representation of number 4 is learnt. The diagram is taken from one of my favorite books, Deep Learning with Python by Francois Chollet
One may note that there are four different successive layers through which data passes before being classified as digit 4. From the above diagram, you may note that the neural network transforms the digit image into representations that are increasingly different from the original image and increasingly informative about the final result. Thus, the model (neural network) learns different representations of data such as those above in order to identify the digit. In modern deep learning models , hundreds of layered representations of data is learnt from the training data.
If the number of layered representations which need to be learnt are one or two, the learning is called as shallow learning and the model is termed as shallow neural network. In case, the large number of representations need to be learnt, the learning is called as deep learning and the model is called as deep neural network. The deep learning, at times, is also termed as layered representations learning or hierarchical representations learning.
Check out my latest book titled as First Principles Thinking: Building winning products using first principles thinking.
- Agentic Reasoning Design Patterns in AI: Examples - October 18, 2024
- LLMs for Adaptive Learning & Personalized Education - October 8, 2024
- Sparse Mixture of Experts (MoE) Models: Examples - October 6, 2024
I found it very helpful. However the differences are not too understandable for me